Quality control and filtering results from cellranger

Sample info and environment setup

PRJNA732205

setwd("/media/jacopo/Elements/re_align/MM/PRJNA732205/SAMN19314091/SRR14629353/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree 
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)

Load and process cellranger data

Load and do the QC for the cellranger data

#list.files(".")
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial, 
    "\nNumber of genes:",  dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 6336 
## Number of genes: 36601

Quality Control

Empty cells were already filtered, check for % mt RNA and death markers:

# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 3
max_counts = 50000



# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt"))  + geom_hline(yintercept=mt_rna, linetype = "dotted")

plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1 

plot2

##  cells retained by mt RNA content ( 3 %): 5665 
##  percentage of retained cells: 89.41 %
## cells retained by counts ( 50000 ): 5654 
##  percentage of retained cells: 89.24 %

Check the distribution of the cells with low counts and control death markers:

min_counts = 250


hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")

hist(dat@meta.data$nCount_RNA, breaks = 1000, xlab = "Counts", xlim = c(0,5000))

hist(dat@meta.data$nCount_RNA, breaks = 10000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)

The evident peak of cells with < 200 counts could contain dying cells.

# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)

# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)

# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)

# Print the most highly expressed genes
head(meanCounts, 30)
##      IGLC2        HBB      IGHG1      IGHG3       IGKC       HBA2      IGHGP 
## 47.8337875  5.9536785  5.4059946  5.1771117  4.5449591  3.3106267  2.9128065 
##        B2M     MALAT1      IGHA1      IGLC3   IGLV6-57       SSR4   IGHV3-73 
##  2.4686649  1.8474114  1.4223433  1.3814714  1.3051771  1.0517711  0.8147139 
##     JCHAIN      IGLC1       HBA1      RPLP1       MZB1     TMSB4X      HLA-B 
##  0.6675749  0.6103542  0.5967302  0.5940054  0.5286104  0.4877384  0.4713896 
##      RPL41      RPL10       EIF1        FTL      RPL13      RPS14      RPS18 
##  0.4495913  0.4277929  0.4005450  0.3405995  0.3351499  0.3242507  0.3133515 
##     RPL13A      RPL21 
##  0.2888283  0.2724796
## cells retained by counts ( 250 ): 5287 
##  percentage of retained cells: 83.44 %

dir.create("result")
saveRDS(dat, file = "./result/SAMN19314091_clean_QC.Rds")

Feature selection

#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)

Data scaling

Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering

# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data

all.genes <- rownames(dat)

dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))

Dimensionality reduction

dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
print(dat[["pca"]], dims = 1:5, nfeatures = 5)
## PC_ 1 
## Positive:  HBA1, HBA2, HBB, SLC25A37, ALAS2 
## Negative:  RPL10, RPL13A, RPS14, EEF1A1, RPS18 
## PC_ 2 
## Positive:  MZB1, IGLC3, IGHG2, FKBP11, SEC11C 
## Negative:  HBA1, HBA2, HBB, LY6E, CD52 
## PC_ 3 
## Positive:  RPL13A, RPL34, RPS3A, RPS23, RPS18 
## Negative:  HLA-B, GADD45B, JUNB, LDHA, H3F3B 
## PC_ 4 
## Positive:  ITM2C, MZB1, IGHA1, DERL3, FKBP11 
## Negative:  HBA1, HBA2, HBB, LINC01781, SLC25A37 
## PC_ 5 
## Positive:  IGKC, GADD45B, CYTOR, HSPA1B, MCL1 
## Negative:  IGLC3, QPCT, CCND3, SEC11C, COMMD3

UMAP

UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:

dat <- FindNeighbors(dat, dims = 1:20)

The graph now can be used as input for the function runUMAP()

dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)

Final plots:

## QC metrics

## markers